preflight documents
This block is part of the anthropic group and was last modified in core v15.0.0.
preflight documents v15.0.0 Convert several documents to clean Markdown with a cheap model, in parallel. Returns one .md file per input plus the concatenated Markdown; run before sending an upload set to an expensive model.
- flow
flow - connection required
anthropicconnection - files required
fileThe documents to convert (multiple). Text and spreadsheets convert for free; PDFs/images/HTML use a cheap model.
- model
valueModel for the conversion. Defaults to claude-haiku-4-5 (cheap). • Suggestions:
claude-haiku-4-5claude-sonnet-4-6 - max tokens
numberMax Markdown tokens per document. Defaults to 16000.
- flow
flow - connection
anthropicconnection - success
condition - files
fileOne cleaned .md file per input; wire straight into a message block's attachments pin.
- markdown
valueAll documents' Markdown concatenated.
- cost
numberTotal USD cost of the conversions (0 for text/spreadsheet).
- usage
object - count
numberNumber of documents processed.
- partial
value - warnings
array<value>Non-fatal notices: unsupported_format (a file type can't be converted), cost_unknown.
- errors
array<value>Error codes when a conversion fails (success=false): config_error, internal_error, model_not_allowed, budget_exceeded, concurrency_limit_exceeded, rate_limited, refused, max_tokens, transport_error.
- error detail
value
preflight files |
documents to markdown |
bulk preflight |
clean documents |
batch ocr |
A typical wiring for preflight documents: a function trigger starts the flow; get file from assets feeds the files pin; the flow out pin feeds debug.

Version history
Introduced in v15.0.0.
Back to
anthropic Return to the main group to view all sub-groups Back to anthropic Return to the group to view all blocks within this group
